diffusion-models

Wunjo CE: Face Swap, Lip Sync, Control Remove Objects & Text & Background, Restyling, Audio Separator, Clone Voice, Video Generation. Open Source, Local & Free.

3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation

Next-token prediction in JavaScript — build fast language and diffusion models.

A customizable image rendering service built on Sogni Supernet SDK

Interactive visual intuition for DDPM (denoising diffusion probabilistic models) — trained in PyTorch, replayed as a static browser page.

Long-form, project-driven guides for learning modern AI from first principles: PyTorch, LLMs, diffusion, RL, robotics, multimodal, inference, and hardware.

🩺 Automate knee MRI segmentation using DiffuKnee’s diffusion model and U-Net pipeline for accurate and efficient multi-class results.

Comic book generator using LLM and diffusion models

This is a simple web tool that allows you to generate images from text prompts using artificial intelligence.

Tiled VAE fix: run PrismML's Bonsai-Image 4B WebGPU at 512px+ on GPUs without shader-f16 (GTX 10xx / Pascal & older). Root cause analysis + 1.4KB patch, no quality loss on f16 devices.

Mental Health Game built for Hackathon

The official implementation of SPICE in Photoshop.

Original reference implementation of "UDT: Unsupervised Discovery of Transformations between Fine-Grained Classes in Diffusion Models"

Personal Knowledge Base & Technical Research Hub by Ahmed BARGADY (AI Engineer & PhD Student @ UM6P). Comprehensive mathematical derivations, PyTorch/DGL code implementations, APT threat detection syntheses (GNNs & Provenance Graphs), and Agentic GraphRAG system architectures.

Guess the missing parts of the prompt! A story is generated by the AI along with the images, you're required to guess the missing parts of the prompt!

A premium SaaS OS for crystallographic analysis. Combines real-time 2D-FFT physics engines with Diffusion Models, YOLO computer vision, and an Agentic AI Copilot to automate S/TEM micrograph research.

[2024 Social Problem-Solving Volunteer Idea Hackathon 1st Place Winner] Generative Volunteer Reward System for Creating "My Own Characters" using GenAI, GreenThread

Provide easy access to 158 free coding models from 20 providers for development and research with Node.js support and open licensing.

Build structured prompts with reference media for MiniMax H3 video model in ComfyUI.

CVPR2026-Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration